This is one of known hardest parts of RL. The short answer is human feedback.
But this is easier said than done. Current models require vastly more learning events than humans, making direct supervision infeasable. One strategy is to train models on human supervisors, so they can bear the bulk of the supervision. This is tricky, but has proven more effective than direct supervision.
But, in my experience, AIs don't specifically struggle with the "qualitative" side of things per-se. In fact, they're great at things like word choice, color theory, etc. Rather, they struggle to understand continuity, consequence and to combine disparate sources of input. They also suck at differentiating fact from fabrication. To speculate wildly, it feels like it's missing the the RL of living in the "real world". In order to eat, sleep and breath, you must operate within the bounds of physics and society and live forever with the consequences of an ever-growing history of choices.
Whenever I watch Claude Code or Codex get stuck trying to force a square peg into a round hole and failing over and over it makes me wish that they could feel the creeping sense of uncertainty and dread a human would in that situation after failure after failure.
Which eventually forces you to take a step back and start questioning basic assumptions until (hopefully) you get a spark of realization of the flaws in your original plan, and then recalibrate based on that new understanding and tackle it totally differently.
But instead I watch Claude struggling to find a directory it expects to see and running random npm commands until it comes to the conclusion that, somehow, node_modules was corrupted mysteriously and therefore it needs to wipe everything node related and manually rebuild the project config by vague memory.
Because no big deal, if it’s wrong it’s the human's problem to untangle and Anthropic gets paid either way so why not try?
> But instead I watch Claude struggling to find a directory it expects to see and running random npm commands until it comes to the conclusion that, somehow, node_modules was corrupted mysteriously and therefore it needs to wipe everything node related and manually rebuild the project config by vague memory.
In fairness I have on many an occasion worked with real life software developers who really should know better deciding the problem lies anywhere but their initial model of how this should work. Quite often that developer has been me, although I like to hope I've learned to be more skeptical when that thought crosses my mind now.
Right, but typically making those kind of mistakes creates more work for yourself and with the benefit of experience you get better at recognizing the red flags to avoid getting in that situation again. but it
Which is why I think the parent post had a great observation about human problem solving having evolved in a universe inherently formed by the additive effect of every previous decision you've ever made made in your life.
There's a lot of variance in humans, sure, but inescapable stakes/skin in the game from an instinctual understanding that you can't just revert to a previous checkpoint any time you screw up. That world model of decisions and consequences helps ground abstract problem solving ability with a healthy amount of risk aversion and caution that LLMs lack.
While we might agreed that language is foundational to what it is to be human, it's myopic to think its the only thing. LLMs are based on training sets of language (period).
But this is easier said than done. Current models require vastly more learning events than humans, making direct supervision infeasable. One strategy is to train models on human supervisors, so they can bear the bulk of the supervision. This is tricky, but has proven more effective than direct supervision.
But, in my experience, AIs don't specifically struggle with the "qualitative" side of things per-se. In fact, they're great at things like word choice, color theory, etc. Rather, they struggle to understand continuity, consequence and to combine disparate sources of input. They also suck at differentiating fact from fabrication. To speculate wildly, it feels like it's missing the the RL of living in the "real world". In order to eat, sleep and breath, you must operate within the bounds of physics and society and live forever with the consequences of an ever-growing history of choices.